{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ssamba-self-supervised-audio-representation","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","arxiv_id":"2405.11831","date":"2024-05-20","proceeding":null,"authors":["Siavash Shams","Sukru Samet Dindar","Xilin Jiang","Nima Mesgarani"],"abstract":"Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and computational inference time, affecting their efficiency. Recently, state space models (SSMs) like Mamba have emerged as a promising alternative, offering a more efficient approach by avoiding these complexities. Given these advantages, we explore the potential of SSM-based models in audio tasks. In this paper, we introduce Self-Supervised Audio Mamba (SSAMBA), the first self-supervised, attention-free, and SSM-based model for audio representation learning. SSAMBA leverages the bidirectional Mamba to capture complex audio patterns effectively. We incorporate a self-supervised pretraining framework that optimizes both discriminative and generative objectives, enabling the model to learn robust audio representations from large-scale, unlabeled datasets. We evaluated SSAMBA on various tasks such as audio classification, keyword spotting, and speaker identification. Our results demonstrate that SSAMBA outperforms the Self-Supervised Audio Spectrogram Transformer (SSAST) in most tasks. Notably, SSAMBA is approximately 92.7% faster in batch inference speed and 95.4% more memory-efficient than SSAST for the tiny model size with an input token size of 22k. These efficiency gains, combined with superior performance, underscore the effectiveness of SSAMBA's architectural innovation, making it a compelling choice for a wide range of audio processing applications.","url_abs":"https://arxiv.org/abs/2405.11831v2","url_pdf":"https://arxiv.org/pdf/2405.11831v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ssamba-self-supervised-audio-representation","repo_url":"https://github.com/siavashshams/ssamba","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"keyword-spotting","task_name":"Keyword Spotting"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speaker-identification","task_name":"Speaker Identification"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keyword-spotting-on-google-speech-commands","task":"Keyword Spotting","dataset":"Google Speech Commands","model":"SSAMBA","rank_in_archive_order":12,"of":42,"metrics":{"Google Speech Commands V1 12":"96.9","Google Speech Commands V2 35":"97.4"},"uses_additional_data":false},{"leaderboard":"/sota/keyword-spotting-on-google-speech-commands-v2-3","task":"Keyword Spotting","dataset":"Google Speech Commands V2 35","model":"SSAMBA","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy (10-fold)":"97.4"},"uses_additional_data":true},{"leaderboard":"/sota/speaker-identification-on-voxceleb1","task":"Speaker Identification","dataset":"VoxCeleb1","model":"SSAMBA","rank_in_archive_order":10,"of":12,"metrics":{"Accuracy":"70.1","Number of Params":"99M","Top-1 (%)":"70.1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.11831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11831"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/siavashshams/ssamba","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_honours":1,"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ced6bc2bfdfe0059","entry":"get_sinusoid_encoding","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/models/both_models.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/models/both_models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ced6bc2bfdfe0059"}},{"code_sha256_prefix":"c15efdd12442aeb4","entry":"lookup_list","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c15efdd12442aeb4"}},{"code_sha256_prefix":"a8fb3f62e2a901d7","entry":"make_index_dict","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8fb3f62e2a901d7"}},{"code_sha256_prefix":"cbf115a314bcd23e","entry":"make_name_dict","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cbf115a314bcd23e"}},{"code_sha256_prefix":"ecb5ae1f3a358b96","entry":"validate_ensemble","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/traintest.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ecb5ae1f3a358b96"}},{"code_sha256_prefix":"47a913b63f142555","entry":"validate","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/traintest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"47a913b63f142555"}},{"code_sha256_prefix":"e181203f02ddc634","entry":"validate_wa","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/traintest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e181203f02ddc634"}},{"code_sha256_prefix":"b48605e2b08b9ca3","entry":"validatemask","repo":"siavashshams/ssamba","repo_kind":"official","path":"src/traintest_mask.py","file_url":"https://github.com/siavashshams/ssamba/blob/HEAD/src/traintest_mask.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b48605e2b08b9ca3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}